Asking machines to identify images

  • Thread starter Thread starter Ryan_m_b
  • Start date Start date
  • Tags Tags
    Images Machines
Click For Summary

Discussion Overview

The discussion revolves around the capabilities and implications of image recognition neural networks, particularly how they can identify and modify images from random noise through iterative processes. Participants explore the nature of pattern recognition, the methods used in traditional image processing, and the psychological parallels that can be drawn from the neural network's behavior.

Discussion Character

  • Exploratory
  • Technical explanation
  • Conceptual clarification
  • Debate/contested

Main Points Raised

  • Some participants find the process of neural networks identifying and modifying images from noise to be fascinating, describing the results as bizarre or beautiful.
  • There is a contention regarding the term "pattern recognition," with some arguing that the neural networks are not performing true pattern recognition but rather creating illusions or false patterns.
  • Participants discuss traditional mathematical methods for pattern recognition, such as Fourier transforms and Hough transforms, suggesting these are more rigorous than the neural network approach.
  • One participant describes a specific example of using Fourier transforms to extract features from noisy images, illustrating a technical method for image processing.
  • Another participant raises concerns about the quality of sources linked in the discussion, suggesting that better original sources should be referenced.
  • There is a proposal that the feedback loop in neural networks could reflect human psychological phenomena such as confirmation bias and pareidolia.

Areas of Agreement / Disagreement

Participants express differing views on the nature of pattern recognition and the effectiveness of neural networks compared to traditional methods. The discussion remains unresolved regarding the validity of the neural network's approach and the implications of its outputs.

Contextual Notes

Some participants reference specific mathematical techniques and their applications, but there is no consensus on the superiority of these methods over neural network approaches. The discussion also touches on the subjective interpretation of the images produced by the neural networks.

Who May Find This Useful

This discussion may be of interest to those exploring artificial intelligence, image processing techniques, and the psychological implications of machine learning outputs.

Ryan_m_b
Staff Emeritus
Science Advisor
Homework Helper
Insights Author
Messages
5,964
Reaction score
727
I can't get over how cool/creepy this is. Researchers took image recognition neural networks and asked them to look for certain images in random noise and once identified modify the image to highlight the pattern. That new image is fed back into the machine and it's asked to do the same again. After multiple repetitions the pictures are bizarre, beautiful or both.

http://www.theguardian.com/technolo...twork-androids-dream-electric-sheep?CMP=fb_gu
 
  • Like
Likes   Reactions: Czcibor, Silicon Waffle and ShayanJ
Computer science news on Phys.org
Ryan_m_b said:
Researchers took image recognition neural networks and asked them to look for certain images in random noise and once identified modify the image to highlight the pattern.
I see what you mean ( by most of the images ). I would not call it "pattern recognition" but rather a LSD-trip.

But I think you know, that "real" pattern recognition uses mathematical rigid methods like Fourier-transforms, Hough-transforms, lens correcting functions, amongst other methods, to measure what is going on in an industrial production ?
 
What a cool idea!
 
Hesch said:
I see what you mean ( by most of the images ). I would not call it "pattern recognition" but rather a LSD-trip.

What makes it not pattern recognition? It's not necessarily good pattern recognition initially given that the machine is detecting patterns that aren't there but after it has edited them in slightly subsequent tests detect that patter.

Hesch said:
But I think you know, that "real" pattern recognition uses mathematical rigid methods like Fourier-transforms, Hough-transforms, lens correcting functions, amongst other methods, to measure what is going on in an industrial production ?

Why would you think I know that and what makes any of that "real"?
 
  • Like
Likes   Reactions: Silicon Waffle
That is cool. They can arrange an exhibition.
 
Ryan_m_b said:
Why would you think I know that and what makes any of that "real"?

Sorry, I thought you meant it as a joke.

I think that this example is real:
dba52883-3a65-4e46-bb08-8c15678642b1-bestSizeAvailable.png

The original photo is "filled" with noise which has some distinct feature. You Fourier transform (FT) the noisy picture and will find this feature in the Fourier transform. Remove it from the transform and make the inverse Fourier transform (IFT). Then you'll get the picture to the right.

Say you have a photo of a car driving by. Due to the speed of the car ( crossing the photo with a shutter time = 1/100 sec. ) the car will be blurred on the photo. Now you take two sheets of paper, draw a dot on one of them and a line on the other ( blurred dot ). The line must exactly be as long as the car has been moving on the photo. Also their moving angle must be the same. FT the dot-picture to D, FT the line-picture to L, FT the photo of the car to C. Then:

IFT( C * ( D / L ) ) and you will have a photo of the car, where you can read its registration number.

Hough transforms are used to recognize lines, circles, parabolas and other mathematical shapes. If such a "known" shape occurs in some photo, the Hough transform will find it and will determine its exact size and location within 1/10 of a pixel-distance. Having a "standard-length" as well in the picture, a computer can calculate very accurate dimension in the picture, check "ovality?" as of things meant to be circular, and so on.

Remember that working machines are often moving very fast, thus the human eye sees nothing. A camera needs perhaps 2μs, using a stroboscope, to see everything in the picture ( well, at least after the computer has calculated for another 100ms ).
 
Last edited:
  • Like
Likes   Reactions: Silicon Waffle
we just start with an existing image and give it to our neural net. We ask the network: “Whatever you see there, I want more of it!” This creates a feedback loop: if a cloud looks a little bit like a bird, the network will make it look more like a bird. This in turn will make the network recognize the bird even more strongly on the next pass and so forth, until a highly detailed bird appears, seemingly out of nowhere.
What intrigues me about these images is that they could be used to illustrate similar human psychological and neurological flaws, from confirmation bias, through delusion and pareidolia, all the way to hallucination. In fact, I wonder if the exact same kind of feedback loop isn't at work in all those things.